Modeling Word Relatedness in Latent Dirichlet Allocation

2014/11/10 by Xun Wang, Wang, Xun
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.AI #cs.CL

paper · pdf · doi:10.48550/arxiv.1411.2328

arxiv created 2014/11/10 · arxiv updated 2014/11/11

Abstract

Standard LDA model suffers the problem that the topic assignment of each word is independent and word correlation hence is neglected. To address this problem, in this paper, we propose a model called Word Related Latent Dirichlet Allocation (WR-LDA) by incorporating word correlation into LDA topic models. This leads to new capabilities that standard LDA model does not have such as estimating infrequently occurring words or multi-language topic modeling. Experimental results demonstrate the effectiveness of our model compared with standard LDA.

Related

• Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey
• More Than Words: Collocation Tokenization for Latent Dirichlet Allocation Models
• Variable Selection for Latent Dirichlet Allocation
• Improving Reliability of Latent Dirichlet Allocation by Assessing Its Stability Using Clustering Techniques on Replicated Runs
• LDAExplore: Visualizing Topic Models Generated Using Latent Dirichlet Allocation